A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Learning automata: an introduction
Learning automata: an introduction
Dynamic Growing Self-organizing Neural Network for Clustering
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Hi-index | 0.00 |
A game-theoretic formulation of adaptive categorization mechanism for ART-type networks is proposed in this paper.W e have derived the game-theoretic model ΓAC for competitive processes of categorization of ART-type networks and an update rule for vigilance parameters using the concept of learning automata.Num bers of clusters generated by ART adaptive categorization are similar regardless of the initial vigilance parameters ρ assigned to the ART networks as demonstrated in the experiments provided.The proposed ART adaptive categorization mechanism can thus avoid the problem of choosing suitable vigilance parameter a priori for pattern categorization.